Stride and Translation Invariance in CNNs
- URL: http://arxiv.org/abs/2103.10097v1
- Date: Thu, 18 Mar 2021 09:17:06 GMT
- Title: Stride and Translation Invariance in CNNs
- Authors: Coenraad Mouton, Johannes C. Myburgh, Marelie H. Davel
- Abstract summary: We show that stride can greatly benefit translation invariance given that it is combined with sufficient similarity between neighbouring pixels.
We also explore the efficacy of other solutions proposed, namely global average pooling, anti-aliasing, and data augmentation.
- Score: 2.4213989921339847
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Convolutional Neural Networks have become the standard for image
classification tasks, however, these architectures are not invariant to
translations of the input image. This lack of invariance is attributed to the
use of stride which ignores the sampling theorem, and fully connected layers
which lack spatial reasoning. We show that stride can greatly benefit
translation invariance given that it is combined with sufficient similarity
between neighbouring pixels, a characteristic which we refer to as local
homogeneity. We also observe that this characteristic is dataset-specific and
dictates the relationship between pooling kernel size and stride required for
translation invariance. Furthermore we find that a trade-off exists between
generalization and translation invariance in the case of pooling kernel size,
as larger kernel sizes lead to better invariance but poorer generalization.
Finally we explore the efficacy of other solutions proposed, namely global
average pooling, anti-aliasing, and data augmentation, both empirically and
through the lens of local homogeneity.
Related papers
- Masked Discriminators for Content-Consistent Unpaired Image-to-Image
Translation [1.3654846342364308]
A common goal of unpaired image-to-image translation is to preserve content consistency between source images and translated images.
We show that masking the inputs of a global discriminator for both domains with a content-based mask is sufficient to reduce content inconsistencies significantly.
In our experiments, we show that our method achieves state-of-the-art performance in photorealistic sim-to-real translation and weather translation.
arXiv Detail & Related papers (2023-09-22T21:32:07Z) - Smooth image-to-image translations with latent space interpolations [64.8170758294427]
Multi-domain image-to-image (I2I) translations can transform a source image according to the style of a target domain.
We show that our regularization techniques can improve the state-of-the-art I2I translations by a large margin.
arXiv Detail & Related papers (2022-10-03T11:57:30Z) - On the Inconsistency of Kernel Ridgeless Regression in Fixed Dimensions [16.704246627541103]
We show that an important class of predictors, kernel machines with translation-invariant kernels, does not exhibit benign overfitting in fixed dimensions.
Our results apply to commonly used translation-invariant kernels such as Gaussian, Laplace, and Cauchy.
arXiv Detail & Related papers (2022-05-26T17:43:20Z) - SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic
Segmentation [52.62441404064957]
Domain adaptive semantic segmentation attempts to make satisfactory dense predictions on an unlabeled target domain by utilizing the model trained on a labeled source domain.
Many methods tend to alleviate noisy pseudo labels, however, they ignore intrinsic connections among cross-domain pixels with similar semantic concepts.
We propose Semantic-Guided Pixel Contrast (SePiCo), a novel one-stage adaptation framework that highlights the semantic concepts of individual pixel.
arXiv Detail & Related papers (2022-04-19T11:16:29Z) - Group Equivariant Subsampling [60.53371517247382]
Subsampling is used in convolutional neural networks (CNNs) in the form of pooling or strided convolutions.
We first introduce translation equivariant subsampling/upsampling layers that can be used to construct exact translation equivariant CNNs.
We then generalise these layers beyond translations to general groups, thus proposing group equivariant subsampling/upsampling.
arXiv Detail & Related papers (2021-06-10T16:14:00Z) - Tracking translation invariance in CNNs [2.4213989921339847]
We investigate the effect of different architectural components of a standard CNN on that network's sensitivity to translation.
By varying convolutional kernel sizes and amounts of zero padding, we control the size of the feature maps produced.
We also measure translation invariance at different locations within the CNN to determine the extent to which convolutional and fully connected layers, respectively, contribute to the translation invariance of a CNN as a whole.
arXiv Detail & Related papers (2021-04-13T08:05:56Z) - Learning Invariances in Neural Networks [51.20867785006147]
We show how to parameterize a distribution over augmentations and optimize the training loss simultaneously with respect to the network parameters and augmentation parameters.
We can recover the correct set and extent of invariances on image classification, regression, segmentation, and molecular property prediction from a large space of augmentations.
arXiv Detail & Related papers (2020-10-22T17:18:48Z) - Attentive Normalization for Conditional Image Generation [126.08247355367043]
We characterize long-range dependence with attentive normalization (AN), which is an extension to traditional instance normalization.
Compared with self-attention GAN, our attentive normalization does not need to measure the correlation of all locations.
Experiments on class-conditional image generation and semantic inpainting verify the efficacy of our proposed module.
arXiv Detail & Related papers (2020-04-08T06:12:25Z) - Generalizing Convolutional Neural Networks for Equivariance to Lie
Groups on Arbitrary Continuous Data [52.78581260260455]
We propose a general method to construct a convolutional layer that is equivariant to transformations from any specified Lie group.
We apply the same model architecture to images, ball-and-stick molecular data, and Hamiltonian dynamical systems.
arXiv Detail & Related papers (2020-02-25T17:40:38Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.